Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 4 of the 14 sources its claims cite were checked for support.
Abstract
Intelligent transportation systems (ITSs) derive significant advantages from advanced models like YOLOv8, which excel in predicting traffic incidents in dynamic urban environments. Roboflow plays a crucial role in organizing and preparing image data essential for computer vision models. Initially, a dataset of 1000 images is utilized for training, with an additional 500 images reserved for validation purposes. Subsequently, the Deep Simple Online and Real-time Tracking (Deep-SORT) algorithm enhances scene analyses over time, offering continuous monitoring of vehicle behavior. Following this, the YOLOv8 model is deployed to detect specific traffic incidents effectively. By combining YOLOv8 with Deep SORT, urban traffic patterns are accurately detected and analyzed with high precision. The findings demonstrate that YOLOv8 achieves an accuracy of 98.4%, significantly surpassing alternative methodologies. Moreover, the proposed approach exhibits outstanding performance in the recall (97.2%), precision (98.5%), and F1 score (95.7%), underscoring its superior capability in accurate prediction and analyses of traffic incidents with high precision and efficiency.
Overview
CoChat Summary
TL;DR
This paper integrates Roboflow, Deep-SORT, and YOLOv8 to detect traffic incidents from surveillance video, training on a traffic-incident image dataset. It reports YOLOv8 accuracy of 98.4%, recall of 97.2%, precision of 98.5%, and F1 score of 95.7%, outperforming several alternative methods.
Key findings
- YOLOv8 achieved accuracy 98.4%, recall 97.2%, precision 98.5%, and F1 score 95.7%, which the paper says are greater than traditional methods.
- The reported YOLOv8 accuracy of 98.4% is higher than Faster R-CNN (87.97%), FA-YOLO (92.95%), and FESSD (83%).
- The precision-recall curve reports “all classes 0.933 mAP@0.5,” while the F1-confidence curve reports an F1 score of 0.89 or 89%.
- Training losses dropped steadily over 40 epochs; mAP@0.5 stabilized around epoch 20, and mAP for IoU 0.50–0.95 showed an overall increasing trend.
Methods
- Roboflow was used for data compilation and annotation; the dataset came from a publicly accessible Kaggle library of 523 traffic incident photos, with Pascal VOC annotations converted to COCO format and split 70:20:10 (335 training, 144 validation, 44 testing). Data augmentation using zooming, contrast correction, and image rotation added 756 photos.
- Deep-SORT was used to scrutinize scenes over time and track vehicle behavior, while YOLOv8 was used for object detection and traffic incident detection; the model was trained through OpenCV and Google Colab and recognizes four categories: “car,” “truck,” “bus,” and “accident.”
- Evaluation used metrics including mAP, accuracy, recall, precision, classification loss, and differential loss, with comparisons to Faster R-CNN, FA-YOLO, FESSD, and YOLO variants.
Limitations
- The paper does not state a dedicated limitations section; it notes that no external funding was received and that data will be made available upon request.
- Evident from the text: dataset size and split are inconsistently reported—the abstract says 1000 images for training and 500 for validation, while the methods section says 523 images split into 335 training, 144 validation, and 44 testing, with 756 photos added through augmentation.
- Evident from the text: the F1 score is reported as 95.7% in the abstract, results, and conclusion but as 0.89 or 89% in Section 3.5, and no external validation or real-world deployment details are provided.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
4 Valid · 0 Not valid · 10 Not checked · 24 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the proposed approach exhibits outstanding performance in the recall (97.2%), precision (98.5%), and F1 score (95.7%)”
- Also stated in: § 3. Results and Discussion · plain
“The model shows the accuracy (98.4%), recall (97.2%), precision (98.5%), and F1 score (95.7%) of the proposed approach”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3. Results and Discussion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the proposed approach exhibits outstanding performance in the recall (97.2%), precision (98.5%), and F1 score (95.7%)”
- Also stated in: § 3. Results and Discussion · plain
“The model shows the accuracy (98.4%), recall (97.2%), precision (98.5%), and F1 score (95.7%) of the proposed approach”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3. Results and Discussion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the proposed approach exhibits outstanding performance in the recall (97.2%), precision (98.5%), and F1 score (95.7%)”
- Also stated in: § 3. Results and Discussion · plain
“The model shows the accuracy (98.4%), recall (97.2%), precision (98.5%), and F1 score (95.7%) of the proposed approach”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3. Results and Discussion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The findings demonstrate that YOLOv8 achieves an accuracy of 98.4%, significantly surpassing alternative methodologies.”
- Also stated in: § 3. Results and Discussion · plain
“The model shows the accuracy (98.4%), recall (97.2%), precision (98.5%), and F1 score (95.7%) of the proposed approach, which are greater than traditional methods.”
- Also stated in: § 3. Results and Discussion · plain
“The accuracy of the YOLOv8 (98.4%) is greater than Faster R-CNN (87.97%),FA-YOLO (92.95%), and FESSD (83%).”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3. Results and Discussion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Mean average precision (mAP) and the mAP for IoU = 0.50 showed volatility before stabilizing at about epoch 20, in contrast to the mAP for IoU between 0.50 and 0.95, which, as seen in Figure 9, displays an overall increasing trend.”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 3.2. Recall-Confidence
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
6 more claims
Create a free account to see all 38 claims and to verify the 2 references still open.
- Probably not a substantial claim. 16
- It may state two separate claims as one. 21
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 3. Results and Discussion
“The model shows the accuracy (98.4%), recall (97.2%), precision (98.5%), and F1 score (95.7%) of the proposed approach”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 3.5. F1 Score
“The YOLOv8 model achieved an F1 score of 0.89 or 89% as shown in Figure 12.”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > Abstract
“Initially, a dataset of 1000 images is utilized for training, with an additional 500 images reserved for validation purposes.”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 17 Our Proposed Study 2024 YOLOv8
“The initial dataset comprised 523 images, with 335 images designated for training, 144 for validation, and 44 for testing purposes.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 2.3. Data Annotation
“The pothole detection algorithm was then trained and tested using these annotated photos.”
§ Visual Detection of Traffic Incident through Automatic Monitoring of Vehicle Activities > 2.2. Dataset
“The authors trained the YOLOV8 model using the preprocessed and divided dataset.”
Citations
Cites
Fontaras, G., Zacharof, N.-G., & Ciuffo, B. (2017) · Progress in Energy and Combustion Science · doi:10.1016/j.pecs.2016.12.004 · Cited by 686
An improved fire detection approach based on YOLO-v8 for smart cities
Talaat, F. M., & ZainEldin, H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08809-1 · Cited by 642
Javed, A. R., Shahzad, F., Rehman, S. U., Zikria, Y. B., Razzak, I., Jalil, Z., & Xu, G. (2022) · Cities · doi:10.1016/j.cities.2022.103794 · Cited by 606
Moving towards smart cities: Solutions that lead to the Smart City Transformation Framework
Kumar, H., Singh, M. K., Gupta, M. P., & Madaan, J. (2020) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2018.04.024 · Cited by 530
Nikitas, A., Michalakopoulou, K., Njoya, E. T., & Karampatzakis, D. (2020) · Sustainability · doi:10.3390/su12072789 · Cited by 495
Unmanned aerial vehicles applications in future smart cities
Mohamed, N., Al-Jaroodi, J., Jawhar, I., Idries, A., & Mohammed, F. (2020) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2018.05.004 · Cited by 449
Net emission reductions from electric cars and heat pumps in 59 world regions over time
Knobloch, F., Hanssen, S. V., Lam, A., Pollitt, H., Salas, P., Chewpreecha, U., Huijbregts, M. A. J., & Mercure, J.-F. (2020) · Nature Sustainability · doi:10.1038/s41893-020-0488-7 · Cited by 407
A detection algorithm for cherry fruits based on the improved YOLO-v4 model
Gai, R., Chen, N., & Yuan, H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-021-06029-z · Cited by 388
Bhushan, B., Khamparia, A., Sagayam, K. M., Sharma, S. K., Ahad, M. A., & Debnath, N. C. (2020) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102360 · Cited by 353
A Review of Technical Standards for Smart Cities
Lai, C. S., Jia, Y., Dong, Z., Wang, D., Tao, Y., Lai, Q. H., Wong, R. T. K., Zobaa, A. F., Wu, R., & Lai, L. L. (2020) · Clean Technologies · doi:10.3390/cleantechnol2030019 · Cited by 351
Research works printed but not linked: 1
- 13. Handiso, A.; Mekebo, G.G.; Galdassa, A. Trends and determinants of road traffic accident human death in Kembata Tembaro zone, SNNPR, Ethiopia. Sci. J. Appl. Math. Stat. 2022, 10, 85-89.
Cited by
Çakıl, F., & Aksoy, N. (2025) · Energy · doi:10.1016/j.energy.2025.135475 · Cited by 32
Real-time rapid accident detection for optimizing road safety in Bangladesh
Arefin, M. S., Mahin, M. I. S., & Mily, F. A. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e42432 · Cited by 21
“Their model, trained on a dataset consisting of 1000 images for training and 500 for validation, demonstrates exceptional performance, achieving 98.4% accuracy, with a recall of 97.2%, precision of 98.5%, and an F1 score of 95.7%, highlighting its effectiveness in predicting traffic incidents [25].”
InfluentialUnsigned Road Incidents Detection Using Improved RESNET From Driver-View Images
Li, C., Wang, B., Zheng, J., Zhang, Y., & Chen, C. L. P. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3515938 · Cited by 6
“Karim et al. [55] proposed an incident detection method based on YOLOv8.”
Khadidos, A. O., Manoharan, H., Khadidos, A. O., Selvarajan, S., Alsufyani, H., & Alanazi, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-91917-w · Cited by 11
Deep Learning-Based Stopped Vehicle Detection Method Utilizing In-Vehicle Dashcams
Park, J., Lee, J., Park, Y., & Lim, Y. (2024) · Electronics · doi:10.3390/electronics13204097 · Cited by 4
Porto, J. V. D. A., Szemes, P. T., Pistori, H., & Menyhárt, J. (2025) · IEEE Access · doi:10.1109/access.2025.3565901 · Cited by 4
“This is seen in applications such as accident prevention, as presented by [14], or simply to improve traffic flow by reducing unnecessary vehicle idling through intelligent traffic light control, as proposed by [20].”
A Comprehensive Analysis of Incident and Object Detection in Traffic Environments
Kovačovič, P., Pirník, R., Tichý, T., Kafková, J., Gašpar, G., & Kuchár, P. (2026) · Smart Cities · doi:10.3390/smartcities9030041 · Cited by 5
Cunanan, J. R. G. M., Baluyot, D. O., Gatdula, M. C. Y., et al. (2024) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3719384.3719408 · Cited by 1
Computer vision-based real-time vehicle and traffic management and classification system
Bahadure, N. B., Parashar, D., Patni, J. C., et al. (2025) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon65728.2025.11071088 · Cited by 1
Investigating Traffic Accident Detection by Using Multimodal Large Language Models
Skender, I., Tong, K., Solmaz, S., et al. (2025) · IEEE International Automated Vehicle Validation Conference (IAVVC) · doi:10.1109/iavvc61942.2025.11219530 · Cited by 1
“Karim et al. [12] employed YOLOv8 to detect vehicles and accidents in real time from surveillance video.”
A hybrid CNN-ViT based framework for automatic traffic actions detection in smart cities
Karaduman, M., Han, N., Karaduman, G., Yıldırım, M., Cho, Y., & Nam, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0339796 · Cited by 2
“By training the YOLOv8 model with a dataset and performing real-time monitoring with Deep-SORT, they detected traffic incidents with 98.4% accuracy [11].”
InfluentialChen, G., Liu, L., Mao, J., et al. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114482 · Cited by 1
Red Light, Real-Time — AI-Powered Traffic Monitoring System
Muralisridharan, B., Mokshith, G., Nair, M. C., Velvizhi, R., & Dharani, V. (2026) · International Conference on Visual Analytics and Data Visualization (ICVADV) · doi:10.1109/icvadv67766.2026.11469766 · Cited by 1
“For instance, research by Adi et al. [4] specifically targeted two-wheeler violation detection systems, and Karim et al. [5] suggested motor vehicle activity monitoring for accident detection.”
Intelligent Urban Traffic Management Using AI and IoT
Golani, R. R., & Bhardwaj, J. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5727-0.ch007
Vision-based Multi-Object Tracking for Unstructured and Congested Indian Roads
Lekshmi, V., & Naveen Prasad, S. (2025) · doi:10.1109/icrm66809.2025.11349048
“The necessity of applying advanced computer vision techniques to observe traffic and avoid accidents in such dynamic environments is being realized more and more [13].”
Multimodal Agentic System for Highway Safety Monitoring
Almarzooqi, A., Abderrazek, A., & Karray, F. (2025) · Computing, Communications and IoT Applications (ComComAp) · doi:10.1109/comcomap68359.2025.11353134
Green Governance in Smart Transportation
Trejo-Macotela, F. R., & Vidal-Cuevas (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-6736-1.ch010
Praveen., E., Prabhukumar, D., Revathy, S., et al. (2025) · International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF) · doi:10.1109/iceconf65644.2025.11379593
“In response to the growing demand for cost-effective, intelligent mobility platforms, researchers and developers have explored various low-cost microcontroller-based AGV models [6].”
Traffic Violations Control Using Deep Learning
Srivastava, D., & Litoriya, R. (2026) · International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) · doi:10.1109/idciot67589.2026.11455678
A Deep Learning-Based Approach to Traffic Accident Evidence Extraction
Meiju, Y., ChenKai, W., & Qi, A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461372
AI-Powered Real-Time Vehicle Detection and Traffic Analysis using YOLOv3 and OpenCV
Kumar, S. N., Hemalatha, A., Malathi, P., et al. (2026) · International Conference on Electronic Systems and Intelligent Computing (ICESIC) · doi:10.1109/icesic67389.2026.11496571
“The ability of machine learning algorithms to automate this process with high precision makes them an indispensable part of contemporary traffic monitoring systems [10].”
Automatic Vehicle Accident Detection and Classification from Images Using YOLOv8
Bhowmik, E., Bhardwaj, P., Khan, A. U., Behera, D. K., Chaudhury, K. S., & Kar, B. (2026) · International Conference on Intelligent Computing, Networks, and Security (IC-ICNS) · doi:10.1109/ic-icns68863.2026.11537436 · Cited by 1
“Abdul Karim et al. [4] approached traffic incident detection using YOLO and automatic vehicle behavior analysis.”
Metadata
- Authors
- Karim, A., Raza, M. A., Alharthi, Y. Z., Abbas, G., Othmen, S., Hossain, M. S., Nahar, A., & Mercorelli, P.
- Affiliations
- Mehran University of Engineering and Technology (PK)
- University of Hafr Al-Batin (SA)
- Southeast University (CN)
- Northern Border University (SA)
- International University of Business Agriculture and Technology (BD)
- American International University-Bangladesh (BD)
- Leuphana University of Lüneburg (DE)
- Corresponding author
- Othmen, Salwa
- Mercorelli, Paolo
- ORCID
- Venue
- World Electric Vehicle Journal
- Publisher
- MDPI AG
- Published
- 2024-08-23
- Volume
- 15
- Issue
- 9
- Pages
- 382
- ISSN
- 2032-6653 (ISSN-L)
- OpenAlex
- W4401805438
- Semantic Scholar
- b738bfadc79ab2d17c348c9cc3f36882403dbe05
- Cited by
- 23
- References
- 79
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 3
- FWCI
- 3.20
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- World Electric Vehicle Journal (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Multilingual Matters (Channel View Publications) (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- traffic incident detection, YOLOv8, DeepSORT, object tracking, intelligent transportation systems, urban traffic, Roboflow dataset, real-time video analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.